July 20, 2018
Pulmonary Sarcoidosis
The Scadding staging system for sarcoidosis, based on the visual assessment of chest radiography, poorly predicts disease progression
Using radiomics, can we create disease subtypes that better predict disease progression for sarcoidosis?
Can we identify 3D regions of the lung where disease exists?
Can we compare disease across lungs between different subtypes?
Using radiomics, can we create disease subtypes that better predict disease progression for sarcoidosis?
Can we identify 3D regions of the lung where disease exists?
Can we compare disease across lungs between different subtypes?
Challenges: EMPIRE10 (Murphy et al. 2011)
Registration Method: Symmetric Normalization (SyN)
Registration object:
buildTemplateResult: Population-level mask in initial template space
Result: Initial template mask in population-level space
Result: Population-level mask in population-level space
lungct R packageMethod: Thresholding based (Mostly)
Identification of lung and airways by thresholding and connected components.
Elimination of airways from part (1) by thresholding, connected components, and dilation.
Identification of left/right lungs by centroid of connected components, erosion and dilation.
lungct R packagelibrary(ANTsRCore)
img = antsImageRead("img.nii.gz")
library(lungct)
mask = segment_lung_lr(img, lthresh = -300)
lungct and 3D SlicerData: Non-smoking healthy controls from COPDGene (n=98)
Results: Dice Similarity Coefficient across all masks
ANTsRlibrary(ANTsRCore)
# Read in registration objects
fixed_mask = antsImageRead("fixed_mask.nii.gz")
moving_mask = antsImageRead("moving_mask.nii.gz")
moving_img = antsImageRead("moving_img.nii.gz")
# Register objects
reg = antsRegistration(fixed = fixed_mask,
moving = moving_mask,
typeofTransform = "SyN",
outprefix = "transformations")
# Apply transformation to image
warped_img = antsApplyTransforms(fixed = fixed_mask,
moving = moving_img,
transformlist = reg$fwdtransforms,
interpolator = "linear")
get_template, available in lungctBased on ANTs buildTemplate
Data: Right-lung, masked CT scans from non-smoking, healthy COPDGene patients (n=10)
Method: Ten iterations of get_template
Results: